在大型语言模型上进行深度数据研究：评估深度数据研究
Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models
AI总结：
本文提出深度数据研究（DDR）任务和DDR-Bench基准，评估大型语言模型的探索智能，发现有效探索需要内在策略而非单纯扩展。
摘要：
Agentic Large Language Models 的代理预期超越正确回答，要求模型自主设定目标和决定探索方向。我们称其为探索智能，区别于仅完成任务的执行智能。数据科学提供自然测试场，因为现实分析从原始数据而非明确查询开始，但很少有基准关注此领域。为此，我们引入深度数据研究（DDR），一个开放任务，使 LLM 自主从数据库提取关键洞察，并提出 DDR-Bench，一个大规模、基于清单的基准，支持可验证评估。结果表明，尽管前沿模型显示出新兴自主性，但长周期探索仍具挑战性。我们的分析强调，有效的探索智能不仅依赖代理支架或单纯扩展，还依赖于 agentic 模型的内在策略。
英文摘要：
The agency expected of Agentic Large Language Models goes beyond answering correctly, requiring autonomy to set goals and decide what to explore. We term this investigatory intelligence, distinguishing it from executional intelligence, which merely completes assigned tasks. Data Science provides a natural testbed, as real-world analysis starts from raw data rather than explicit queries, yet few benchmarks focus on it. To address this, we introduce Deep Data Research (DDR), an open-ended task where LLMs autonomously extract key insights from databases, and DDR-Bench, a large-scale, checklist-based benchmark that enables verifiable evaluation. Results show that while frontier models display emerging agency, long-horizon exploration remains challenging. Our analysis highlights that effective investigatory intelligence depends not only on agent scaffolding or merely scaling, but also on intrinsic strategies of agentic models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
